© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 10777
    Prev
    Next
    INDEX
    Explanations

    words associated with data analysis in technical papers.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     )
    -0.70
     ]
    -0.66
     »
    -0.66
     );
    -0.61
     ),
    -0.60
     }
    -0.60
     
    -0.59
     !
    -0.58
     »,
    -0.57
     ).
    -0.56
    POSITIVE LOGITS
     myſelf
    1.06
     Monfieur
    0.96
     Theſe
    0.95
     Majefty
    0.94
     itſelf
    0.94
     للمعارف
    0.91
     ſeveral
    0.90
     themſelves
    0.90
     Anſ
    0.89
    ########.
    0.88
    Activations Density 0.811%

    No Known Activations